{"id":10866,"date":"2024-03-22T10:03:11","date_gmt":"2024-03-22T10:03:11","guid":{"rendered":"https:\/\/dailyai.com\/?p=10866"},"modified":"2024-03-28T09:32:30","modified_gmt":"2024-03-28T09:32:30","slug":"quiet-star-teaches-language-models-to-think-before-they-speak","status":"publish","type":"post","link":"https:\/\/dailyai.com\/da\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/","title":{"rendered":"Quiet-STaR l\u00e6rer sprogmodeller at t\u00e6nke, f\u00f8r de taler"},"content":{"rendered":"<p><strong>Forskere fra Stanford University og Notbad AI har udviklet Quiet-STaR, en teknik, der tr\u00e6ner en sprogmodel (LM) til at r\u00e6sonnere internt, f\u00f8r den genererer et output.<\/strong><\/p>\n<p>N\u00e5r vi mennesker taler, har vi normalt en indre dialog, som former de ord, vi i sidste ende udtaler. Jo mere vi t\u00e6nker, f\u00f8r vi taler, jo bedre bliver kvaliteten af vores talte ord.<\/p>\n<p><a href=\"https:\/\/arxiv.org\/pdf\/2403.09629.pdf\" target=\"_blank\" rel=\"noopener\">I deres artikel<\/a>beskriver forskerne, hvordan de tr\u00e6nede en LM (<a href=\"https:\/\/dailyai.com\/da\/2024\/02\/mistral-ai-releases-new-model-and-chatbot-to-take-on-gpt-4\/\">Mistral-7B<\/a>) for at l\u00e6re at efterligne denne proces p\u00e5 en generel m\u00e5de. Quiet-STaR er en videreudvikling af en anden teknik kaldet STaR, eller Self-Taught Reasoner.<\/p>\n<p>STaR er en metode til at tr\u00e6ne en model med nogle f\u00e5 eksempler p\u00e5 sp\u00f8rgsm\u00e5l med forklaringer (rationaler) p\u00e5 svarene. Modellen bruger disse eksempler p\u00e5 tankek\u00e6der til at fors\u00f8ge at besvare sp\u00f8rgsm\u00e5l p\u00e5 egen h\u00e5nd og selv finde ud af rationalerne.<\/p>\n<p>STaR evaluerer, om de rationaler, den finder frem til, resulterer i korrekte svar eller ej, og forfiner sine rationaler.<\/p>\n<p>Hvor imponerende STaR end er, er dens evne til at r\u00e6sonnere begr\u00e6nset til sp\u00f8rgsm\u00e5l-svar-sammenh\u00e6nge (QA) under tr\u00e6ningen. M\u00e5let med Quiet-STaR er at give en LM en generaliseret evne til at l\u00e6re at r\u00e6sonnere eller udvikle rationaler p\u00e5 tv\u00e6rs af en bredere vifte af tekster, ikke kun QA-datas\u00e6t.<\/p>\n<h2>Hvordan virker Quiet-STaR?<\/h2>\n<blockquote class=\"twitter-tweet\">\n<p dir=\"ltr\" lang=\"en\">Sprogmodeller i dag er tr\u00e6net til at r\u00e6sonnere enten 1) generelt ved at efterligne online r\u00e6sonneringsdata eller 2) sn\u00e6vert ved selv at l\u00e6re deres egne l\u00f8sninger p\u00e5 specifikke opgaver.<\/p>\n<p>Kan LM'er l\u00e6re sig selv at r\u00e6sonnere generelt?\ud83c\udf1fIntroduktion af Quiet-STaR, selvundervisning via intern monolog!\ud83e\uddf5 <a href=\"https:\/\/t.co\/WCSxLPZeCX\">pic.twitter.com\/WCSxLPZeCX<\/a><\/p>\n<p>- Eric Zelikman (@ericzelikman) <a href=\"https:\/\/twitter.com\/ericzelikman\/status\/1768663835106513041?ref_src=twsrc%5Etfw\">15. marts 2024<\/a><\/p><\/blockquote>\n<p><script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<p>En af de vigtigste nyskabelser i Quiet-STaR er, at den genererer rationaler eller tanker parallelt efter alle symboler i den tekst, den behandler. Den udsender ikke disse tankek\u00e6der, deraf den \"stille\" del af algoritmens navn.<\/p>\n<p>Algoritmen behandler rationalerne gennem et \"blandingshoved\". Hvert rationale evalueres ud fra n\u00f8jagtigheden af den forudsigelse af det n\u00e6ste tegn, som det har produceret, sammenlignet med den forudsigelse, som basismodellen har lavet.<\/p>\n<p>Hvis basismodellen (uden Quiet-STaR) giver en bedre forudsigelse, s\u00e5 var rationalet ikke godt. Hvis begrundelsen resulterer i en mere pr\u00e6cis forudsigelse af det n\u00e6ste token, ved algoritmen, at den har fat i noget godt.<\/p>\n<p>Derefter bruger den en forst\u00e6rkende l\u00e6ringsalgoritme (REINFORCE) til at l\u00e6re, hvilke rationaler der hj\u00e6lper, og hvilke der h\u00e6mmer modellens pr\u00e6station. Resultatet er, at modellen l\u00e6rer en generaliseret evne til at t\u00e6nke, f\u00f8r den forudsiger det n\u00e6ste token.<\/p>\n<h2>Quiet-STaR resultater<\/h2>\n<p>Forskerne testede den Quiet-STaR-uddannede Mistral-7B-model p\u00e5 GSM8K matematik- og CommonsenseQA-benchmarks for sund fornuft. De fandt ud af, at Quiet-STaR forbedrede evnen til forvirring og direkte r\u00e6sonnement med nul skud p\u00e5 b\u00e5de CommonsenseQA (36,3% til 47,2%) og GSM8K (5,9% til 10,9%) benchmarks.<\/p>\n<figure id=\"attachment_10868\" aria-describedby=\"caption-attachment-10868\" style=\"width: 1334px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"size-full wp-image-10868\" src=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Quiet-STaR-benchmark-results.jpg\" alt=\"\" width=\"1334\" height=\"518\" srcset=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Quiet-STaR-benchmark-results.jpg 1334w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Quiet-STaR-benchmark-results-300x116.jpg 300w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Quiet-STaR-benchmark-results-1024x398.jpg 1024w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Quiet-STaR-benchmark-results-768x298.jpg 768w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Quiet-STaR-benchmark-results-370x144.jpg 370w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Quiet-STaR-benchmark-results-800x311.jpg 800w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Quiet-STaR-benchmark-results-740x287.jpg 740w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Quiet-STaR-benchmark-results-20x8.jpg 20w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/Quiet-STaR-benchmark-results-124x48.jpg 124w\" sizes=\"auto, (max-width: 1334px) 100vw, 1334px\" \/><figcaption id=\"caption-attachment-10868\" class=\"wp-caption-text\">Quiet-STaR-resultater p\u00e5 GMSK8-matematik i grundskolen og CommonsenseQA-benchmarks for r\u00e6sonnementer baseret p\u00e5 sund fornuft. Hver linje repr\u00e6senterer en iteration af Quiet-STaR med varierende l\u00e6ngder p\u00e5 tanketokens, og hvor mange tokens foran den r\u00e6sonnerede. Baseline er Mistral-7B uden Quiet-STaR. Kilde: arXiv<\/figcaption><\/figure>\n<p>Mens Mistral-7B's matematiske r\u00e6sonnement stadig ikke er fantastisk, leverede Quiet-STaR en forbedring p\u00e5 n\u00e6sten 85% i forhold til basismodellen, og det var uden nogen datas\u00e6tspecifik finjustering.\"<\/p>\n<p>Testresultaterne viste ogs\u00e5, at forbedringer i pr\u00e6stationerne var direkte relateret til, hvor mange tokens der blev afsat til modellens indre tanker. Jo mere den t\u00e6nkte, f\u00f8r den svarede, jo bedre var svaret.<\/p>\n<p>Disse forbedringer kommer p\u00e5 bekostning af et betydeligt computeroverhead. Den indre monolog, som modellen f\u00f8rer under tankeprocessen, genererer en masse tokens.<\/p>\n<p>Forbedringer i hardware vil i sidste ende g\u00f8re det ekstra overhead, der f\u00f8lger med teknikker som disse, mindre betydningsfuldt.<\/p>\n<p>Forskerne konkluderer, at fremtidigt arbejde med at optimere Quiet-STaR ogs\u00e5 kan hj\u00e6lpe. Dynamisk forudsigelse af, om en tankeproces er p\u00e5kr\u00e6vet, eller hvor lang den skal v\u00e6re, kan sk\u00e6re ned p\u00e5 un\u00f8dvendige tanketokens.<\/p>\n<p>Resultaterne af at tr\u00e6ne en lille model som Mistral-7B med Quiet-STaR er lovende. Forskerne mener, at \"de samme teknikker anvendt p\u00e5 en bedre model sandsynligvis ville give uforholdsm\u00e6ssigt bedre resultater.\"<\/p>\n<h2>Etiske sp\u00f8rgsm\u00e5l<\/h2>\n<p>At f\u00e5 en sprogmodel til at r\u00e6sonnere mere som et menneske medf\u00f8rer nogle interessante problemstillinger og etiske sp\u00f8rgsm\u00e5l.<\/p>\n<p>Forskerne bem\u00e6rker, at \"det er umuligt at vide, om det r\u00e6sonnement, som modellen udtrykker i sproget, n\u00f8jagtigt repr\u00e6senterer modellens interne behandling.\" De begrundelser, som modellen genererer, er naturlige sproglige repr\u00e6sentationer af dens indre r\u00e6sonnementer. Er de en n\u00f8jagtig afspejling?<\/p>\n<p>De bem\u00e6rker desuden, at \"der er ingen beskyttelse mod skadelige eller forudindtagede r\u00e6sonnementer, hvis modellen finder dem nyttige.\"<\/p>\n<p>Vi er m\u00e5ske tilfredse med en AI-models svar, men det er ikke sikkert, at vi kan lide eller forst\u00e5 den tankeproces, der f\u00f8rte til det.<\/p>\n<p>En af artiklens hovedforfattere, Eric Zelikman, har lige sluttet sig til Elon Musks xAI i denne uge. Han vil m\u00e5ske opdage, at <a href=\"https:\/\/dailyai.com\/da\/2024\/03\/elon-musks-xai-open-sources-its-llm-grok-1\/\">Grok<\/a> er mindre optaget af disse etiske sp\u00f8rgsm\u00e5l og mere begejstret for udsigten til AI-fremskridt.<\/p>\n<p>&nbsp;<\/p>","protected":false},"excerpt":{"rendered":"<p>Forskere fra Stanford University og Notbad AI har udviklet Quiet-STaR, en teknik, der tr\u00e6ner en sprogmodel (LM) til at r\u00e6sonnere internt, f\u00f8r den genererer et output. N\u00e5r mennesker taler, har vi normalt en indre dialog, som former de ord, vi til sidst formulerer. Jo mere vi t\u00e6nker, f\u00f8r vi taler, jo bedre bliver kvaliteten af vores talte ord. I deres artikel beskriver forskerne, hvordan de har tr\u00e6net en LM (Mistral-7B) til at l\u00e6re at efterligne denne proces p\u00e5 en generel m\u00e5de. Quiet-STaR er en videreudvikling af en anden teknik kaldet STaR, eller Self-Taught Reasoner. STaR er en metode til at tr\u00e6ne en model med nogle f\u00e5<\/p>","protected":false},"author":6,"featured_media":10869,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[118],"class_list":["post-10866","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-llms"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Quiet-STaR teaches language models to think before they speak | DailyAI<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/dailyai.com\/da\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/\" \/>\n<meta property=\"og:locale\" content=\"da_DK\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Quiet-STaR teaches language models to think before they speak | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Researchers from Stanford University and Notbad AI developed Quiet-STaR, a technique that trains a language model (LM) to reason internally before generating an output. When humans speak, we normally have an inner dialogue that shapes the words we eventually verbalize. The more we think before speaking, the better the quality of our spoken words. In their paper, the researchers describe how they trained an LM (Mistral-7B) to learn how to imitate this process in a generalized way. Quiet-STaR is a progression of another technique called STaR, or Self-Taught Reasoner. STaR is a method of training a model with a few\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/da\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-03-22T10:03:11+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-03-28T09:32:30+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/the-thinker.webp\" \/>\n\t<meta property=\"og:image:width\" content=\"1792\" \/>\n\t<meta property=\"og:image:height\" content=\"1024\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/webp\" \/>\n<meta name=\"author\" content=\"Eugene van der Watt\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:site\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:label1\" content=\"Skrevet af\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Estimeret l\u00e6setid\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutter\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"Quiet-STaR teaches language models to think before they speak\",\"datePublished\":\"2024-03-22T10:03:11+00:00\",\"dateModified\":\"2024-03-28T09:32:30+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/\"},\"wordCount\":808,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/the-thinker.webp\",\"keywords\":[\"LLMS\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"da-DK\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/\",\"name\":\"Quiet-STaR teaches language models to think before they speak | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/the-thinker.webp\",\"datePublished\":\"2024-03-22T10:03:11+00:00\",\"dateModified\":\"2024-03-28T09:32:30+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/#breadcrumb\"},\"inLanguage\":\"da-DK\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"da-DK\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/the-thinker.webp\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/03\\\/the-thinker.webp\",\"width\":1792,\"height\":1024},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/03\\\/quiet-star-teaches-language-models-to-think-before-they-speak\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Quiet-STaR teaches language models to think before they speak\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"name\":\"DailyAI\",\"description\":\"Your Daily Dose of AI News\",\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/dailyai.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"da-DK\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"da-DK\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"width\":4501,\"height\":934,\"caption\":\"DailyAI\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/DailyAIOfficial\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/dailyaiofficial\\\/\",\"https:\\\/\\\/www.youtube.com\\\/@DailyAIOfficial\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\",\"name\":\"Eugene van der Watt\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"da-DK\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"caption\":\"Eugene van der Watt\"},\"description\":\"Eugene comes from an electronic engineering background and loves all things tech. When he takes a break from consuming AI news you'll find him at the snooker table.\",\"sameAs\":[\"www.linkedin.com\\\/in\\\/eugene-van-der-watt-16828119\"],\"url\":\"https:\\\/\\\/dailyai.com\\\/da\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Quiet-STaR l\u00e6rer sprogmodeller at t\u00e6nke, f\u00f8r de taler | DailyAI","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/dailyai.com\/da\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/","og_locale":"da_DK","og_type":"article","og_title":"Quiet-STaR teaches language models to think before they speak | DailyAI","og_description":"Researchers from Stanford University and Notbad AI developed Quiet-STaR, a technique that trains a language model (LM) to reason internally before generating an output. When humans speak, we normally have an inner dialogue that shapes the words we eventually verbalize. The more we think before speaking, the better the quality of our spoken words. In their paper, the researchers describe how they trained an LM (Mistral-7B) to learn how to imitate this process in a generalized way. Quiet-STaR is a progression of another technique called STaR, or Self-Taught Reasoner. STaR is a method of training a model with a few","og_url":"https:\/\/dailyai.com\/da\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/","og_site_name":"DailyAI","article_published_time":"2024-03-22T10:03:11+00:00","article_modified_time":"2024-03-28T09:32:30+00:00","og_image":[{"width":1792,"height":1024,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/the-thinker.webp","type":"image\/webp"}],"author":"Eugene van der Watt","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"Skrevet af":"Eugene van der Watt","Estimeret l\u00e6setid":"4 minutter"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"Quiet-STaR teaches language models to think before they speak","datePublished":"2024-03-22T10:03:11+00:00","dateModified":"2024-03-28T09:32:30+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/"},"wordCount":808,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/the-thinker.webp","keywords":["LLMS"],"articleSection":["Industry"],"inLanguage":"da-DK"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/","url":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/","name":"Quiet-STaR l\u00e6rer sprogmodeller at t\u00e6nke, f\u00f8r de taler | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/the-thinker.webp","datePublished":"2024-03-22T10:03:11+00:00","dateModified":"2024-03-28T09:32:30+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/#breadcrumb"},"inLanguage":"da-DK","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/"]}]},{"@type":"ImageObject","inLanguage":"da-DK","@id":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/the-thinker.webp","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/03\/the-thinker.webp","width":1792,"height":1024},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/03\/quiet-star-teaches-language-models-to-think-before-they-speak\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"Quiet-STaR teaches language models to think before they speak"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DailyAI","description":"Din daglige dosis af AI-nyheder","publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/dailyai.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"da-DK"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"da-DK","@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","width":4501,"height":934,"caption":"DailyAI"},"image":{"@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/DailyAIOfficial","https:\/\/www.linkedin.com\/company\/dailyaiofficial\/","https:\/\/www.youtube.com\/@DailyAIOfficial"]},{"@type":"Person","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa","name":"Eugene van der Watt","image":{"@type":"ImageObject","inLanguage":"da-DK","@id":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","caption":"Eugene van der Watt"},"description":"Eugene har en baggrund som elektronikingeni\u00f8r og elsker alt, hvad der har med teknologi at g\u00f8re. N\u00e5r han tager en pause fra at l\u00e6se AI-nyheder, kan du finde ham ved snookerbordet.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/da\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts\/10866","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/comments?post=10866"}],"version-history":[{"count":5,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts\/10866\/revisions"}],"predecessor-version":[{"id":10873,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts\/10866\/revisions\/10873"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/media\/10869"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/media?parent=10866"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/categories?post=10866"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/tags?post=10866"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}